| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 210, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.523809523809525e-07, | |
| "loss": 2.286, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.904761904761905e-05, | |
| "loss": 1.8049, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1.9505415489478293e-05, | |
| "loss": 1.4705, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.7971325072229227e-05, | |
| "loss": 1.4275, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.4452016353607178, | |
| "eval_runtime": 33.7692, | |
| "eval_samples_per_second": 12.526, | |
| "eval_steps_per_second": 0.118, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 1.5564337355766412e-05, | |
| "loss": 1.2701, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 1.2548028728946548e-05, | |
| "loss": 0.9577, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 9.252699064135759e-06, | |
| "loss": 0.8857, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.039202339608432e-06, | |
| "loss": 0.8585, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.5615026950836182, | |
| "eval_runtime": 33.3263, | |
| "eval_samples_per_second": 12.693, | |
| "eval_steps_per_second": 0.12, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 3.2594314447468457e-06, | |
| "loss": 0.6339, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 1.2177842662977136e-06, | |
| "loss": 0.5752, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 1.3783069908621772e-07, | |
| "loss": 0.5848, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.6578937768936157, | |
| "eval_runtime": 33.3303, | |
| "eval_samples_per_second": 12.691, | |
| "eval_steps_per_second": 0.12, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 210, | |
| "total_flos": 440321248854016.0, | |
| "train_loss": 1.0299149649483816, | |
| "train_runtime": 7625.9144, | |
| "train_samples_per_second": 3.508, | |
| "train_steps_per_second": 0.028 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 210, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 440321248854016.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |